IFN509 Assignment 2: ProjectAssignment type: Project (applied)Topics: Data preparation (cleaning, integration, transformation), data analysis and mining.Weight: 25%Group or Individual: You will work on this assignment in groups of two or three. Note thatonly a single submission is required from each group, however make sure the report submittedcontains the name and student number of each student in the group.Due date: Sunday June 2nd, 23:50pm (end of week 13)Driving questionHow does weather affect air quality in Brisbane, Australia?Data provided :southbrisbane-aq-2018: Daily weather observations in various cities in Australia from July2008 until March 20191.weatherAUS.csv: South Brisbane (South East Queensland) 2018 hourly air quality andmeteorological data2.Analysis required:a) Investigate whether there are any direct correlations between air quality indicatorsand either rain, humidity, wind, or temperatures. Explain what the correlationsmean (you may use visualization if you wish).b) Use decision trees to see if at least one of the average daily air quality indicators canbe predicted on the basis of any or all of the weather indicators provided. Explainwhat patterns the best decision tree highlights.c) Cluster the days and demonstrate through visualization how the clusters areorganized. Explain what patterns they reveal.1 Observations were drawn from numerous weather stations. The daily observations are availablefrom http://www.bom.gov.au/climate/data. Copyright Commonwealth of Australia 2010, Bureau ofMeteorology. Available as a package at https://rattle.togaware.com/weatherAUS.csv2 Environment and Science, Queensland Government, South Brisbane (South East Queensland) 2018hourly air quality and meteorological data API, licensed under Creative Commons Attribution4.0 sourced on 16 May 2019. Available at https://data.qld.gov.au/dataset/air-quality-monitoring-2018/resource/f28488d1-44fc-4fda-aeff-291039d30f70Preparing the data:a) Investigate the quality of the datasets, clean the data where required (addressmissing data and outliers). Explain what decisions you made for cleaning the dataand why.b) Integrate the two provided datasets. You may use manual methods, or externalsources to do so. Explain your approach3.c) Provide the final, clean dataset you have used.Software:Explain which technology/ies you have chosen to use for this project. Explain the limitationsand benefits of your approach. If you are not using MySQL, R, please consult with the unitcoordinator for approval.Submission RequirementsYou are to submit the following files:1. Through the Blackboard link: a) CSV files containing your clean data that you used foranalysiIFN509留学生作业代做、Data preparation作业代写、代写SQL程序语言作业、SQL语言作业代做 调试Ms (import1.csv, import2.csv etc.) b) Source code. You will need to compressseveral files into a .zip file.2. Through the Turnitin link: An 8 pages (maximum) report which contains the followingsections (report.pdf):a. Title, Group members (including student numbers)b. Description of how software was used (1/2 page)c. Data Summary (quality, cleaning, preparation, integration) (2 pages)d. Correlations (1 page)e. Decision Tree (1.5 pages)f. Clusters (1.5 pages)3 You can proceed with the rest of the assignment without integrating the two datasets, and only work withthe air quality dataset. If you chose to do so, you will lose marks in the data quality analysis/and datapreparation sections of the marking scheme, but not in other sections. Marking SchemeMarking is based only on the report, code and dataset are for verification purposes only. ?Task Marks CriteriaExplain choice oftechnology3 - The student described the software they used inthe report : The student described how they usedsoftware in the report, and this evidences that thepackages were used effectively (e.g. MySQL mightbe used for complex joins, Excel for particulargraphs, R for association analysis, another programfor a bubble plot etc.)- The student critically reflected on the benefits andlimitations of their chosen approachData quality analysis 3 - The student explains and illustrates the stepsrequired and applied to prepare the dataset.- Data quality issues are all considered and discussedappropriately.Data preparation 4 - The student correctly cleans the data provided sothat the entire set can be imported into a statisticalpackage for analysis- The student organizes data in a way that is sensiblefor the software they use- Redundant data is removed- Data types are correctly applied- Outliers are removed using a commonly acceptedrule- Methods for cleaning and outlier exclusion aredescribed in the reportVisuals/summary forcorrelations2 The student was able to represent the effectively datato explain.Correlations 2 The student appropriately identified trends in the data.Decision tree 2 The decision tree produced supports the analysisrequiredAnalysis of decisiontree2 The interpretation of the decision tree is correct andwell explainedVisualisation ofclusters2 - The visualization provided is effective to illustratethe nature of the clusters.- A variety of layers are used appropriately.Analysis of clusters 2 Appropriate conclusions were drawn based on thedata set.Presentation 3 - No spelling or grammatical errors were found inthe report- The report is presented professionally- Files are appropriately titled转自：http://www.3daixie.com/contents/11/3444.html